Soft Margin Spectral Normalization for GANs

Computing and Software for Big Science. 2024. Vol. 8. No. 1. Article 12.

Рогачев А. И., Ратников Ф. Д.

In this paper, we explore the use of Generative Adversarial Networks (GANs) to speed up the simulation process while ensuring that the generated results are consistent in terms of physics metrics. Our main focus is the application of spectral normalization for GANs to generate electromagnetic calorimeter (ECAL) response data, which is a crucial component of the LHCb. We propose an approach that allows to balance between model’s capacity and stability during training procedure, compare it with previously published ones and study the relationship between proposed method’s hyperparameters and quality of generated objects. We show that the tuning of normalization method’s hyperparameters boosts the quality of generative model.

Ключевые слова: машинное обучение, глубинное обучение, high energy physics, физика высоких энергий, generative models, генеративные модели, Machine Learning, Deep Learning

ПУБЛИКАЦИЯ ПОДГОТОВЛЕНА ПО РЕЗУЛЬТАТАМ ПРОЕКТА: Исследование точных моделей быстрой симуляции методами машинного обучения: тестирование решений (2024)